Face Corrupt Identification Using LSTM And ResNext

Face Corrupt Identification Using LSTM And ResNext

T. Devanshu Kumar1, P. Ananditha 2, K. Sai Srikari3, G. Anirvaj4, V. Geethika Siri5, G. Sateesh6

[1-5]B.TECH STUDENTS

6Associate Professor, LIET

[1,2,3,4,5] Computer Science and Information Technology, Lendi Institute of Engineering and Technology, Vizianagaram

---------------------------------------------------------------------***---------------------------------------------------------------------

Abstract - People will believe in what they see rather than hidden facts. In recent times as technology is improving and it became very easy to change a particular person in an existing image or video with someone else. So, spreading these types of modified videos causes spamming and peculating wrong information over social media and this will cause the great extent of misleading and threatening to the common people. To overcome these tedious situations, we are building a deep learning model that will identify the genuinity of the video or image in terms of the origin of its source. In our proposed system we are using Long Short-Term Memory and ResNext.

Key Words:  ResNext, Convolution neural network, Recurrent Neural Network (RNN), Long Short- Term Memory (LSTM), Computer vision, Deepfake Video Detection, Pre Processing, Deep Learning, Image Processing, Classification.